Machine learning-enabled prediction of 3D-printed microneedle features

Abstract

Microneedles (MNs) introduced a novel injection alternative to conventional needles, offering a decreased administration pain and phobia along with more efficient transdermal and intradermal drug delivery/sample collecting. 3D printing methods have emerged in the field of MNs for their time- and cost-efficient manufacturing. Tuning 3D printing parameters with artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is an emerging multidisciplinary field for optimization of manufacturing biomedical devices. Herein, we presented an AI framework to assess and predict 3D-printed MN features. Biodegradable MNs were fabricated using fused deposition modeling (FDM) 3D printing technology followed by chemical etching to enhance their geometrical precision. DL was used for quality control and anomaly detection in the fabricated MNAs. Ten different MN designs and various etching exposure doses were used create a data library to train ML models for extraction of similarity metrics in order to predict new fabrication outcomes when the mentioned parameters were adjusted. The integration of AI-enabled prediction with 3D printed MNs will facilitate the development of new healthcare systems and advancement of MNs' biomedical applications.